dplyrこれは質問以上のものだと思いplyrます。速度のために、data.table私が書いたいくつかのコードで使用しています。中間ステップでは、〜 32,000 行のゲノミクス データを含むテーブルがあります。
> bedbin.dt
Source: local data table [32,138 x 4]
Groups: chr
bin start site chr
1 2 3500000 ssCTCF 1
2 3 4000000 ssCTCF+Cohesin 1
3 3 4000000 ssCTCF 1
4 4 4500000 ucCTCF 1
5 4 4500000 ssCTCF+Cohesin 1
6 4 4500000 ssCTCF+Cohesin 1
7 4 4500000 ssCTCF+Cohesin 1
8 4 4500000 ssCTCF 1
9 4 4500000 ssCTCF 1
10 5 5000000 ssCTCF 1
.. ... ... ... ...
編集
または、そのような最初の100行のデータ（指示についてはRicardo Saportaへのthx）
bedbin.dt <- data.table(structure(list(bin = c("2", "3", "3", "4", "4", "4", "4", "4","4", "5", "5", "7", "7", "7", "7", "7", "7", "8", "8", "9", "9","11", "12", "14", "14", "14", "14", "14", "14", "14", "14", "15","15", "15", "15", "15", "15", "15", "15", "15", "15", "16", "16","17", "17", "17", "18", "20", "20", "20", "21", "21", "21", "21","21", "21", "21", "21", "21", "21", "22", "22", "5057", "5057","5057", "5057", "5059", "5059", "5059", "5059", "5059", "5060","5060", "5060", "5060", "5060", "5060", "5061", "5063", "5063","5064", "5064", "5064", "5064", "5064", "5064", "5064", "5064","5064", "5064", "5064", "5064", "5064", "5064", "5064", "5064","5064", "5064", "5064", "5064"), start = c(3500000L, 4000000L,4000000L, 4500000L, 4500000L, 4500000L, 4500000L, 4500000L, 4500000L,5000000L, 5000000L, 6000000L, 6000000L, 6000000L, 6000000L, 6000000L,6000000L, 6500000L, 6500000L, 7000000L, 7000000L, 8000000L, 8500000L,9500000L, 9500000L, 9500000L, 9500000L, 9500000L, 9500000L, 9500000L,9500000L, 10000000L, 10000000L, 10000000L, 10000000L, 10000000L,10000000L, 10000000L, 10000000L, 10000000L, 10000000L, 10500000L,10500000L, 11000000L, 11000000L, 11000000L, 11500000L, 12500000L,12500000L, 12500000L, 13000000L, 13000000L, 13000000L, 13000000L,13000000L, 13000000L, 13000000L, 13000000L, 13000000L, 13000000L,13500000L, 13500000L, 162500000L, 162500000L, 162500000L, 162500000L,163500000L, 163500000L, 163500000L, 163500000L, 163500000L, 164000000L,164000000L, 164000000L, 164000000L, 164000000L, 164000000L, 164500000L,165500000L, 165500000L, 166000000L, 166000000L, 166000000L, 166000000L,166000000L, 166000000L, 166000000L, 166000000L, 166000000L, 166000000L,166000000L, 166000000L, 166000000L, 166000000L, 166000000L, 166000000L,166000000L, 166000000L, 166000000L, 166000000L), site = c("ssCTCF","ssCTCF+Cohesin", "ssCTCF", "ucCTCF", "ssCTCF+Cohesin", "ssCTCF+Cohesin","ssCTCF+Cohesin", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF+Cohesin","ssCTCF", "ssCTCF+Cohesin", "ssCTCF+Cohesin", "ssCTCF", "ucCTCF","ucCTCF", "ucCTCF", "ssCTCF", "ssCTCF", "ssCTCF+Cohesin", "ssCTCF","ssCTCF+Cohesin", "ssCTCF", "ucCTCF", "ucCTCF", "ssCTCF", "ssCTCF+Cohesin","ssCTCF", "ssCTCF+Cohesin", "ssCTCF+Cohesin", "ssCTCF+Cohesin","ssCTCF+Cohesin", "ssCTCF", "ucCTCF", "ssCTCF+Cohesin", "ssCTCF","ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF","ssCTCF", "ssCTCF", "ucCTCF", "ucCTCF", "ucCTCF", "ssCTCF", "ssCTCF","ssCTCF", "ssCTCF", "ssCTCF+Cohesin", "ssCTCF", "ssCTCF", "ssCTCF","ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF+Cohesin", "ucCTCF", "ssCTCF","ssCTCF+Cohesin", "ssCTCF+Cohesin", "ssCTCF", "ucCTCF", "ssCTCF","ssCTCF+Cohesin", "ssCTCF", "ssCTCF", "ucCTCF", "ucCTCF", "ssCTCF","ucCTCF", "ssCTCF", "ucCTCF", "ucCTCF", "ssCTCF", "ssCTCF", "ucCTCF","ucCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ucCTCF", "ucCTCF", "ssCTCF","ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ssCTCF", "ucCTCF","ucCTCF", "ssCTCF+Cohesin", "ucCTCF", "ucCTCF", "ucCTCF"), chr = structure(c(1L,1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 20L, 20L,20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L), .Label = c("1","10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "2","3", "4", "5", "6", "7", "8", "9", "X"), class = "factor")), .Names = c("bin","start", "site", "chr"), sorted = "chr", class = c("data.table","data.frame"), row.names = c(NA, -100L)), key='chr')
編集終了
次に、各行と他のすべての行 (chr でグループ化) のすべての可能な組み合わせを作成したいと考えています。これは他のデータへのクエリ（結合）を形成するので、事前計算するのが最善（そして最も簡単）だと思います：
# grouped by chr column
bedbin.dt = group_by(bedbin.dt, chr)
# an outer like function
outerFun= function(dt)
{
unique(data.table(
x=dt[rep(1:nrow(dt),each =nrow(dt)),],
y=dt[rep.int(1:nrow(dt),times=nrow(dt)),]))
}
> system.time((outer.bedbin.dt = do(bedbin.dt, outerFun1)))
user system elapsed
90.607 13.993 105.536
私の考えでは、これは sloooowwww です...ただし、 、またはordata.frameのような基本関数を使用する場合と比較すると、かなり高速です。ただし、これは実際には私がテストしている小さめのデータセットです。by()lapply()
だから... 誰かがouterFunのより高速なバージョンについてアイデアを持っているかどうか疑問に思っていますか??? またはより速い方法はありますrep()かrep.int()？